Levels TC Analysis

library(tidyverse)
library(ggplot2)  
library(plotly)
library(kableExtra)
library(shiny)
library(tidyr)
library(dplyr)

levels_df <- read.csv("./levels-cleaned.csv")
drop <- c("X", "timestamp")
levels_df <- levels_df[,!(names(levels_df) %in% drop)]
levels_df

pres <- levels_df %>%
  select(company, totalyearlycompensation, 
         title, yearsofexperience, location, gender, lat, long, year)
  
head(pres) %>%
  kbl() %>%
  kable_styling() %>% 
  save_kable("combined_tables.png")

Sys.setenv("MAPBOX_TOKEN" = "pk.eyJ1IjoidGltb3RoeW5ndXllIiwiYSI6ImNrbW8wZmR0OTF6cnoycHQ0ZXFydTBwY3oifQ.LumCjldRn9X9jX70p1BA-w")

Let’s take a look at highest total compensation by entry level candidates

new_entry <- levels_df %>% filter(yearsofexperience <= 1.5)
new_entry

new_entry <- new_entry %>% 
                drop_na(basesalary)  %>%
                drop_na(title) %>%
                drop_na(stockgrantvalue) %>%
                drop_na(bonus)
'
new_entry_tc <- aggregate(new_entry$totalyearlycompensation, 
                          by=list(location=new_entry$location), 
                          FUN=mean, na.action = na.omit)
names(new_entry_tc)[names(new_entry_tc) == "x"] <- "tc"
new_entry_tc
'

[1] "\nnew_entry_tc <- aggregate(new_entry$totalyearlycompensation, \n                          by=list(location=new_entry$location), \n                          FUN=mean, na.action = na.omit)\nnames(new_entry_tc)[names(new_entry_tc) == \"x\"] <- \"tc\"\nnew_entry_tc\n"

new_entry_tc <- aggregate(list(new_entry$totalyearlycompensation,
                               new_entry$basesalary,
                               new_entry$stockgrantvalue,
                               new_entry$bonus), 
                          by=list(location=new_entry$location), 
                          FUN=mean, na.action = na.omit)
names(new_entry_tc)[2] <- "tc"
names(new_entry_tc)[3] <- "basesalary"
names(new_entry_tc)[4] <- "stockgrantvalue"
names(new_entry_tc)[5] <- "bonus"
new_entry_tc

location_df <- new_entry %>% 
  distinct(location, .keep_all = TRUE) %>%
  select(location, zip, lat, long, city, state)
location_df

new_entry_tc <- new_entry_tc %>%
  left_join(location_df)

Joining, by = "location"

new_entry_tc

fig <- new_entry_tc
fig <- fig %>%
  plot_mapbox() %>%
  add_markers(x = ~long,
              y = ~lat,
              color = ~state,
              size = ~tc*100,
              text = ~paste0(location, "<br>",
                 "<b>Mean Yearly Compensation:</b> $", tc, "<br>",
                 "<b>Mean Salary Base:</b> $", basesalary, "<br>",
                 "<b>Mean stocks grants:</b> $", stockgrantvalue, "<br>",
                 "<b>Mean bonus:</b> $", bonus, "<br>")) %>%
  layout(
    mapbox = list(
      style = 'open-street-map',
      center = list(lon = -97, lat = 38),
      zoom = 2.5)) 

fig

Ignoring 9 observations`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.n too large, allowed maximum for palette Set2 is 8
Returning the palette you asked for with that many colors
n too large, allowed maximum for palette Set2 is 8
Returning the palette you asked for with that many colors
Ignoring 9 observations`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.`line.width` does not currently support multiple values.n too large, allowed maximum for palette Set2 is 8
Returning the palette you asked for with that many colors
n too large, allowed maximum for palette Set2 is 8
Returning the palette you asked for with that many colors

 levels_df %>% 
        filter(yearsofexperience >= 1.5)

ui <-
  fluidPage(
    # App title
    titlePanel("Years of Experience, Location & Total Compensation"),
    
    # sidebar layout with input and output definitions
    sidebarLayout(
      # Sidebar panel for inputs
      sidebarPanel(
        sliderInput("yoe",
                    "Years of experience",
                    min = min(levels_df$yearsofexperience),
                    max = max(levels_df$yearsofexperience),
                    value = c(min(levels_df$yearsofexperience), 
                              max(levels_df$yearsofexperience)),
                    step = 1,
                    sep = "")
      ),
      
      # Main panel for displaying outputs
      mainPanel(
        plotlyOutput(outputId = "tc_loc")
      )
    ))
server <- function(input, output) {
  output$tc_loc <-
    renderPlotly({
      prep <- levels_df %>% 
        filter(yearsofexperience >= input$yoe[1] & 
              yearsofexperience <= input$yoe[2]) 
        
        
      tc <- aggregate(prep$totalyearlycompensation, 
                          by=list(location=prep$location), 
                          FUN=mean, na.action = na.omit)
      names(tc)[names(tc) == "x"] <- "tc"
    
      location_df <- prep %>% 
        distinct(location, .keep_all = TRUE) %>%
        select(location, zip, lat, long, city, state)
      
      tc <- tc %>% left_join(location_df)
      
      fig <- tc
      fig %>%
        plot_mapbox() %>%
        add_markers(x = ~long,
                    y = ~lat,
                    color = ~state,
                    size = ~tc*100,
                    text = ~paste0(location, "<br>",
                       "<b>Total Yearly Compensation:</b> $", tc)) %>%
        layout(
          mapbox = list(
            style = 'open-street-map',
            center = list(lon = -97, lat = 38),
            zoom = 2.5)) 
          })
}

shinyApp(ui, server)

Listening on http://127.0.0.1:7419

NA

Looking at different roles in companies based on role

con <- factor(unique(levels_df[c("title")])$title)
con

 [1] Product Manager              Software Engineer            Software Engineering Manager
 [4] Data Scientist               Solution Architect           Technical Program Manager   
 [7] Product Designer             Marketing                    Business Analyst            
[10] Hardware Engineer            Sales                        Recruiter                   
[13] Mechanical Engineer          Management Consultant       
14 Levels: Business Analyst Data Scientist Hardware Engineer Management Consultant Marketing ... Technical Program Manager

• First group by location + company

• Then split by yoe

• If there’s at least a male & female per location + company, include in data. Else exclude

  Let’s begin with an example to see

new_entry <- new_entry %>% 
                drop_na(basesalary)  %>%
                drop_na(title) %>%
                drop_na(stockgrantvalue) %>%
                drop_na(bonus)

new_entry_tc <- aggregate(list(tc = new_entry$totalyearlycompensation,
                               basesalary = new_entry$basesalary,
                               stockgrantvalue = new_entry$stockgrantvalue,
                               bonus = new_entry$bonus), 
                          by=list( title=new_entry$title, state=new_entry$state), 
                          FUN=mean, na.action = na.omit)
#names(new_entry_tc)[2] <- "state"
#names(new_entry_tc)[3] <- "tc"
#names(new_entry_tc)[4] <- "basesalary"
#names(new_entry_tc)[5] <- "stockgrantvalue"
#names(new_entry_tc)[6] <- "bonus"

new_entry_tc

location_df <- new_entry %>% 
  distinct(state, .keep_all = TRUE) %>%
  select(state, lat, long) %>% na.omit()
# location_df <- na.omit(location_df)
location_df

new_entry_tc <- new_entry_tc %>%
  left_join(location_df)

Joining, by = "state"

new_entry_tc

new_entry_tc %>% 
  filter(state == "AR") %>%
  ggplot(aes(x = title, y = tc, fill = title)) +
  geom_text(aes(y = tc, label = tc, hjust=0), 
                  size = 3) +
        geom_bar(stat = "identity")+
        coord_flip()+
        labs(x = "", y = "")+
        ggtitle(paste("Hello"))+
        theme(legend.title = element_blank(), legend.position = "none")